{"id":"W4372260056","doi":"10.1109/icassp49357.2023.10095934","title":"On Weighted Cross-Entropy for Label-Imbalanced Separable Data: An Algorithmic-Stability Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Early stopping; Generalization error; Logarithm; Cross entropy; Gradient descent; Conjecture; Mathematics; Algorithm; Regularization (linguistics); Applied mathematics; Stability (learning theory); Artificial intelligence; Machine learning; Pattern recognition (psychology); Artificial neural network; Discrete mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01645554,0.001882215,0.001840792,0.002768454,0.001147216,0.002629002,0.00216204,0.002336346,0.001999808],"category_scores_gemma":[0.07508127,0.0007560095,0.001289054,0.001435339,0.00562247,0.007940386,0.005384997,0.004831033,0.0005097939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0024646,"about_ca_system_score_gemma":0.001531275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001893381,"about_ca_topic_score_gemma":0.001619102,"domain_scores_codex":[0.9961964,0.001510802,0.0002059929,0.0009223472,0.0008609401,0.0003035179],"domain_scores_gemma":[0.9400509,0.04771322,0.003149307,0.004469175,0.003494683,0.001122786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005432348,0.0002724711,0.01376546,0.0003697925,0.0002270008,0.0003515686,0.00069429,0.6641749,0.006931398,0.228745,0.002812847,0.08111218],"study_design_scores_gemma":[0.00001290112,0.00009187106,0.001014441,0.00004685338,0.00001713933,0.00007266628,0.00003627357,0.9125006,0.001595222,0.08418962,0.0003992731,0.00002311069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06383059,0.001152345,0.9312366,0.001326945,0.00005018453,0.0001053594,0.0001387522,0.0002825402,0.001876617],"genre_scores_gemma":[0.8301689,0.001392922,0.161253,0.0009643231,0.0003667707,0.000384158,0.0008961566,0.0004706169,0.004103105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01645554,"threshold_uncertainty_score":0.08702618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1096811870986246,"score_gpt":0.3856051661873163,"score_spread":0.2759239790886917,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}